The distribution model of velocity in expressway

This paper takes the collection data from the up and downstream of on-ramp in Beijing expressway as the basis of research. After analyzing the traffic flow parameters including flow, speed and occupancy rate, divide the data into two categories: congest and unimpeded states with fuzzy C means clustering method. Then establish the model for the velocity distribution situation in difference position and road lane with kernel density estimation method. And verify the effects of the model with the chi-square test, the results show that the model can pass the test in all traffic states and lane in the expressway the data collected in.